python 抓取图片保存在本地
2015-05-27 13:32
423 查看
import re
import urllib
# Download picture and save in disk
def downImg(url, dirPath, name):
fr = urllib.urlopen(url)
stream = fr.read(-1)
fr.close()
print dirPath+'/'+name
fw = open(dirPath+'/'+name, 'w')
fw.write(stream)
fw.close()
def getPageCode(url, fromCharset, toCharset):
fr = urllib.urlopen(url)
pageCode = fr.read()
fr.close()
return pageCode
def getImgUrl(pageCode):
pattern = re.compile(r'http\://[\w\-\./]+\.jpg')
return re.findall(pattern, pageCode)
def main():
dirPath = '/home/damin/img'
nameEnding = 1
start = 'http://www.22mm.cc/mm/qingliang/'
allUrl = [start+'index.html']
x = 2
while x<=10:
allUrl += [start+'index_'+str(x)+'.html']
x += 1
for url in allUrl:
# 1. get page code
print url
pageCode = getPageCode(url, 'gb2312', 'utf8')
# 2. get all img url
imgUrl = getImgUrl(pageCode)
# 3. download the picture
for src in imgUrl:
filename = 'MM'+ str(nameEnding) +'.jpg'
nameEnding += 1
downImg(src, dirPath, filename)
if __name__ == '__main__':
main()
import urllib
# Download picture and save in disk
def downImg(url, dirPath, name):
fr = urllib.urlopen(url)
stream = fr.read(-1)
fr.close()
print dirPath+'/'+name
fw = open(dirPath+'/'+name, 'w')
fw.write(stream)
fw.close()
def getPageCode(url, fromCharset, toCharset):
fr = urllib.urlopen(url)
pageCode = fr.read()
fr.close()
return pageCode
def getImgUrl(pageCode):
pattern = re.compile(r'http\://[\w\-\./]+\.jpg')
return re.findall(pattern, pageCode)
def main():
dirPath = '/home/damin/img'
nameEnding = 1
start = 'http://www.22mm.cc/mm/qingliang/'
allUrl = [start+'index.html']
x = 2
while x<=10:
allUrl += [start+'index_'+str(x)+'.html']
x += 1
for url in allUrl:
# 1. get page code
print url
pageCode = getPageCode(url, 'gb2312', 'utf8')
# 2. get all img url
imgUrl = getImgUrl(pageCode)
# 3. download the picture
for src in imgUrl:
filename = 'MM'+ str(nameEnding) +'.jpg'
nameEnding += 1
downImg(src, dirPath, filename)
if __name__ == '__main__':
main()
相关文章推荐
- python抓取网页中图片并保存到本地
- 不务正业--用python爬虫抓取Konachan的图片并保存到本地文件
- python抓取网页中图片并保存到本地
- python抓取网页中图片并保存到本地
- python抓取网页中图片并保存到本地
- 黄聪:python访问抓取网页常用命令(保存图片到本地、模拟POST、GET、中文编码问题)
- python抓取网页中图片并保存到本地
- 黄聪:python访问抓取网页常用命令(保存图片到本地、模拟POST、GET、中文编码问题)
- python 解析网页,将抓取到的图片保存到本地
- Python使用爬虫抓取美女图片并保存到本地的方法【测试可用】
- python抓取网页中图片并保存到本地
- Python 爬虫抓取美女图片保存到本地
- python 网页抓取并保存图片
- python爬虫实战(1)抓取网页图片自动保存
- javacv:调取本地摄像头,抓取人脸,保存为图片
- python网络爬虫系列(四) --- 批量抓取并保存图片
- 用ASP.NET实现下载远程图片保存到本地的方法 保存抓取远程图片的方法
- Python抓取网页中的图片到本地
- ASP.NET下载远程图片保存到本地的方法、保存抓取远程图片
- 萌新的Python学习日记 - 爬虫无影 - 使用BeautifulSoup + urlretrieve 抓取并保存图片:weheartit